首款支持退火与储备池计算的65nm混沌处理器，实现边缘AI实时决策。
CBM-Dual: A 65-nm Fully Connected Chaotic Boltzmann Machine Processor for Dual Function Simulated Annealing and Reservoir Computing
- 设计专用调度器与乘法拆分方案，降低99%计算量和59%面积。
- 1024神经元全连接混沌玻尔兹曼机，实测能效比退火/储备池任务分别提升25-54倍、4.5倍。
- 适合边缘智能中需轻量化实时推理的场景，如自动驾驶、工业检测。
本文提出CBM-Dual，首个经硅片验证的数字混沌动力学处理器（CDP），支持模拟退火（SA）与储备池计算（RC）。该芯片面向自主边缘AI的实时决策与轻量化自适应需求，采用最大规模全连接1024神经元混沌玻尔兹曼机（CBM）。为解决数字CDP高计算与面积开销问题，提出：1）基于神经元翻转率低特性的专用调度器，减少99%乘加操作；2）高效乘法拆分方案，降低59%面积。在65nm工艺下（12mm²）实现异构任务并行执行，达到业界领先能效，使SA与RC任务性能分别提升×25-54和×4.5倍。
原文摘要 · Abstract (English)
This paper presents CBM-Dual, the first silicon-proven digital chaotic dynamics processor (CDP) supporting both simulated annealing (SA) and reservoir computing (RC). CBM-Dual enables real-time decision-making and lightweight adaptation for autonomous Edge AI, employing the largest-scale fully connected 1024-neuron chaotic Boltzmann machine (CBM). To address the high computational and area costs of digital CDPs, we propose: 1) a CBM-specific scheduler that exploits an inherently low neuron flip rate to reduce multiply-accumulate operations by 99%, and 2) an efficient multiply splitting scheme that reduces the area by 59%. Fabricated in 65nm (12mm$^2$), CBM-Dual achieves simultaneous heterogeneous task execution and state-of-the-art energy efficiency, delivering $\times$25-54 and $\times$4.5 improvements in the SA and RC fields, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。